SeizEAR Safety Study for Epilepsy Detection
This study is testing a new in-ear device called SeizEAR to see if it can safely and effectively detect seizures. The SeizEAR device fits in your ear canal and measures electrical signals. Researchers want to see how well it works compared to the standard scalp-based EEG (electroencephalogram), which measures brain activity. Initially, the study will enroll 5 healthy volunteers aged 18 to 70 who have no history of seizures. If successful, 10 participants with seizures or suspected seizures will then test the device. The main goals are to measure how accurately SeizEAR detects seizures (sensitivity, F1 score, and positive predictive value) over 16 weeks. The study status is currently unclear.
- Study design
- This is an interventional study planning to enroll 15 participants. It will first test 5 healthy individuals, then 10 participants with seizures or suspected seizures.
- What's involved
- Not specified in the trial record.
- Compensation
- Not stated in the trial record.
- Follow-up
- The main measurements for this study will be taken at week 16.
AI-generated from the public study record. Only the study team can confirm whether you're eligible — confirm details with them before making decisions.
SeizEAR Safety Study
At a glance
Conditions
Where it's being run
1 sites across 1 statesStudy leadership
- Ho Wing (Andy) Chan, MD · PRINCIPAL_INVESTIGATOR · Icahn School of Medicine at Mount Sinai
Who to contact
Opens a ready-to-send draft in your own email app — review before sending.
Do you actually qualify for this trial?
Add a private profile and we'll compare every criterion below against your situation — and tell you which ones are met, uncertain, or excluding.
Inclusion
Exclusion
What this trial measures
- Sensitivityat week 16
The sensitivity of ear-EEG will be measured by sensitivity the percentage of ear-EEG predictions that overlap with conventional EEG annotations for at least 1 second per 24 hours accordingly. The ear-EEG annotations will be considered as predictions and the conventional EEG annotations as the truth. Any prediction was deemed true if they overlap at least 1 second with the truth. All seizure annotations were either true positive (TP), false positive (FP), or false negative (FN).
- F1 scoreat week 16
The Device F1 Score is a metric used to evaluate the performance of the ear-EEG device in detecting seizures. It is the harmonic mean of precision and recall, providing a balance between these two metrics. Precision is the proportion of true positive (TP) predictions out of all positive predictions (TP + FP), while recall (or sensitivity) is the proportion of true positive (TP) predictions out of all actual seizure events. The F1 Score ranges from 0 to 1, with higher scores indicating better performance in accurately detecting seizures. The performance of ear-EEG will be measured by the device F1 score per 24 hours accordingly.
- Positive predictive value (PPV)at week 16
The Device Positive Predictive Value (PPV) is calculated by dividing the number of true positives (TP) by the total number of positive test results (TP + FP), where FP represents false positives. PPV measures the accuracy of the ear-EEG device in predicting seizures, indicating the likelihood that a positive prediction made by the device is a true seizure event. The PPV ranges from 0 to 1, with higher values indicating better accuracy in predicting seizures. The performance of ear-EEG will be measured by the positive predictive value (PPV) per 24 hours accordingly.
- False detection rateat week 16
The Device False Detection Rate is a metric used to evaluate the performance of the ear-EEG device in terms of false positives. It is calculated by dividing the number of false positives (FP) by the total number of test results (TP + FP + FN), where TP represents true positives and FN represents false negatives. The false detection rate is typically expressed as the number of false positive predictions per 24 hours. Lower values indicate better performance, with fewer false alarms generated by the device.. The performance of ear-EEG will be measured by false detection rate per 24 hours accordingly.
- Comfort Rating Scaleat week 16
The Comfort Rating Scale is a 6-item questionnaire that asks participants about their comfort with the device. Responses are on a 5-point Likert scale ranging from 0 (not comfortable at all) to 5 (completely comfortable). The items assessed include tightness, weight, security, softness, overall comfort, and overall fit of the device in the ear. Total scores range from 0 to 30, with higher scores indicating greater comfort.